20260503T001007Z-legal_extraction_v2-graft-soft-valid-b10-4b-3k-6b84f8b8 – AI Model by paulo037 | AlphaNeural AI

You can deploy this model and start earning money today!

paulo037/
20260503T001007Z-legal_extraction_v2-graft-soft-valid-b10-4b-3k-6b84f8b8

like

0

text-generation

Qwen/Qwen3-VL-4B-Instruct

Views

No views yet

20260503T001007Z-legal_extraction_v2-graft-soft-valid-b10-4b-3k-6b84f8b8

This model is a fine-tuned version of Qwen/Qwen3-VL-4B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1048
Graft/constrained Ratio: 1.0
Graft/constrained Tokens: 53933.0
Graft/fallback Samples: 0.0
Graft/standard Fallback Samples: 0.0

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 4
seed: 14
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.03
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Ratio	Tokens	Samples	Fallback Samples
0.0668	0.3303	27	0.1012	1.0	69377.0	0.0	0.0
0.0381	0.6606	54	0.0993	1.0	50808.0	0.0	0.0
0.0333	0.9908	81	0.1004	1.0	38265.0	0.0	0.0
0.027	1.3180	108	0.1003	1.0	28908.0	0.0	0.0
0.0301	1.6483	135	0.0991	1.0	58447.0	0.0	0.0
0.0246	1.9786	162	0.0980	1.0	51038.0	0.0	0.0
0.0195	2.3058	189	0.1023	1.0	40722.0	0.0	0.0
0.0208	2.6361	216	0.1058	1.0	28908.0	0.0	0.0
0.0176	2.9664	243	0.1048	1.0	53933.0	0.0	0.0

Framework versions

PEFT 0.17.1
Transformers 4.57.0
Pytorch 2.11.0a0+eb65b36914.nv26.02
Datasets 4.1.1
Tokenizers 0.22.2